Sleep Detection Demo
A demo is provided to showcase the capabilities of the sleep detect model. Similar to other modes, the demo can be invoked either via CLI or within sleepkit python package. At a high level, the demo performs the following actions based on the provided configuration parameters:
- Load the configuration file (e.g.
demo.json) - Load the desired dataset features (e.g.
fs004) - Load the trained model (e.g.
sleep-detect) - Load random test subject's data
- Perform inference either on PC or EVB
- Generate report
Usage
PC backend
- Create / modify configuration file (e.g.
demo.json) - Ensure "pc" is selected as the backend in configuration file.
- Run demo
sleepkit --mode demo --task detect --config ./configs/sleep-detect/demo.json - HTML report will be saved to
${job_dir}/report.html
EVB backend
- Create / modify configuration file (e.g.
demo.json) - Ensure "evb" is selected as the backend in configuration file.
- Plug EVB into PC via two USB-C cables.
- Build and flash firmware to EVB
cd evb && make && make deploy - Run demo
sleepkit --mode demo --task detect --config ./configs/sleep-detect/demo.json - HTML report will be saved to
${job_dir}/report.html